Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15794
    Prev
    Next
    INDEX
    Explanations

    academic or technical terms and possibly statistics related to basketball players and games

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1445
    +0.12
    0.4%
    1699
    +0.12
    0.4%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.12
    0.04
    924
    +0.12
    0.04
    1445
    +0.11
    0.04
    Negative Logits
     gaily
    -1.19
     intrigu
    -1.10
     shenan
    -1.05
     unspeak
    -1.04
     maneu
    -1.03
     withal
    -1.03
     homeward
    -1.02
     pamph
    -1.02
     indestru
    -1.02
     sophistic
    -1.01
    POSITIVE LOGITS
     poichè
    0.68
    &
    
    0.67
    XmlEnum
    0.66
    çalves
    0.64
     lenker
    0.64
     "..\..\..\
    0.63
     nessuna
    0.63
     LIRE
    0.61
    naldo
    0.61
     affinch
    0.59
    Activations Density 0.282%

    No Known Activations